Accelerating Material Science with AI
Alibaba AI Agent Discovers Four New Superconductors
DAMO Academy’s ElementsClaw system analyzed 2.4 million structures in 28 hours to identify new materials.
A digital visualization of a molecular crystal structure displayed on a monitor in a modern scientific laboratory, representing AI-driven material discovery.
Photo: Avantgarde News
Alibaba DAMO Academy researchers, in partnership with several Chinese universities, introduced ElementsClaw, an AI agent for material discovery [1][2]. The system analyzed 2.4 million crystal structures in just 28 GPU hours to find potential superconductors [1][3].
The AI identified 68,000 potential candidates during its initial screening process [1]. Using these results, researchers successfully synthesized and verified four entirely new superconducting materials [1][2]. This breakthrough demonstrates how AI can significantly reduce the time required for complex scientific experimentation [2].
Editorial notes
Transparency note
AI assisted drafting. Human edited and reviewed.
- AI assisted
- Yes
- Human review
- Yes
- Last updated
Risk assessment
Reviewed for sourcing quality and editorial consistency.
Sources
- 1.↗
pandaily.com
https://pandaily.com/alibaba-damo-elementsclaw-ai-superconductors-28-gpu-hours-jul2026
- 2.↗
scmp.com
https://www.scmp.com/tech/big-tech/article/3359335/alibabas-elements-claw-ai-agent-unearths-four-new-superconductors
- 3.↗
finance.biggo.com
https://finance.biggo.com/news/2414f7e6-4d3f-4950-9d4a-6e87cb1a3802
Related stories
View all
Topics
About the author
Avantgarde News Desk covers accelerating material science with ai and editorial analysis for Avantgarde News.